Appearance-Based Virtual View Generation of Temporally-Varying Events from Multi-Camera Images in the 3D Room

Abstract

In this paper, we present an "appearance-based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method, we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 29, 1999
Accession Number
ADA363762

Entities

People

  • Hideo Salto
  • Makoto Kimura
  • Shigeyuki Baba
  • Sundar Vedula
  • Takeo Kanade

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Computer Science
  • Computers
  • Demographic Cohorts
  • Disparities
  • Equations
  • Geometry
  • Image Processing
  • Images
  • Interpolation
  • Light Sources
  • Recovery
  • Sequences
  • Signal Generators
  • Triangles
  • Video
  • Video Signals

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Image Processing and Computer Vision.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.